Advisory Software Engineer

Description

Lenovo Research is seeking an experienced Software Engineer to join the On-Device Intelligence team within the PC Innovation and Ecosystem organization. This team focuses on developing software and runtime capabilities that enable AI models to run efficiently and reliably on Lenovo PCs, combining on-device inference, internal PC sensor signals, and intelligent user-context algorithms.

The ideal candidate will design, implement, optimize, and debug production-quality software for on-device AI model deployment and runtime execution. They will collaborate closely with researchers, platform engineers, and product teams to integrate AI models into Windows-based PC experiences, enhance latency, reduce memory usage, improve power efficiency, and ensure system reliability. Additionally, they will translate research concepts into robust prototypes, demos, and product-ready components.

Basic Qualifications

• BS or MS degree in Computer Science, Computer Engineering, Electrical Engineering, or a related technical field
• 5+ years of professional software development experience, preferably in building Windows applications, system components, SDKs, services, or runtime software
• Strong programming skills in C++ and Python, with a solid understanding of data structures, algorithms, debugging, multithreading, optimization, and design
• Hands-on experience deploying, integrating, or optimizing AI/ML models for on-device or edge inference environments
• Experience working with AI inference runtimes or model deployment frameworks such as ONNX Runtime, TFLite, PyTorch Mobile, DirectML, OpenVINO, RyzenAI, or similar technologies
• Understanding of model deployment tradeoffs including latency, memory footprint, power consumption, accuracy, hardware acceleration, and runtime stability

Preferred Qualifications

• Experience building AI runtime components, inference pipelines, model loading/execution flows, or abstraction layers for multiple model formats and hardware backends
• Familiarity with model optimization techniques such as quantization, pruning, distillation, operator fusion, batching, caching, or hardware-specific acceleration
• Experience with PC, edge, or embedded hardware acceleration technologies such as CPU, GPU, NPU, DSP, DirectML, CUDA, OpenCL, or vendor-specific AI accelerators
• Experience integrating AI features into Windows applications, background services, device software, or user-facing PC experiences
• Strong engineering practices, including Git, unit testing, profiling, CI/CD, code review, technical documentation, and cross-functional collaboration